Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
arXiv:1605.02019
Abstract
Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe lda2vec, a model that learns dense word vectors jointly with Dirichlet-distributed latent document-level mixtures of topic vectors. In contrast to continuous dense document representations, this formulation produces sparse, interpretable document mixtures through a non-negative simplex constraint. Our method is simple to incorporate into existing automatic differentiation frameworks and allows for unsupervised document representations geared for use by scientists while simultaneously learning word vectors and the linear relationships between them.
arXiv commentSubmitted to CoNLL 2016
References in corpus (5)
Cited by in corpus (11)
- Structural Text Segmentation of Legal Documents
- Network representation learning systematic review: ancestors and current development state
- Exploring the evolution of research topics during the COVID-19 pandemic
- Improving Document Classification with Multi-Sense Embeddings
- SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations
- P-SIF: Document Embeddings Using Partition Averaging
- Discovering topics with neural topic models built from PLSA assumptions
- Mixing syntagmatic and paradigmatic information for concept detection
- Can questions summarize a corpus? Using question generation for characterizing COVID-19 research
- From Talk to Action with Accountability: Monitoring the Public Discussion of Policy Makers with Deep Neural Networks and Topic Modelling
- Column2Vec: Structural Understanding via Distributed Representations of Database Schemas